According to a recent study from Yale University, dual-eligible patients — those enrolled in both Medicare and Medicaid — ended up being readmitted 30 days after discharge than those who were not dual-eligible. but, Yale study It was also found that these differences in dual-eligible Medicare patients were not directly related to differences in social determinants of health (SDOH), even after adjusting for social and health service availability factors at the community and state levels.
The study used census data to explore the causes of 30-day readmission rates for 2.5 million U.S. adults age 65 or older, to understand what contributed to the increased readmission rates for some patients. The study’s final sample included 898,395 patients admitted for heart failure, 475,444 patients admitted for acute myocardial infarction, and 1,214,282 patients admitted for pneumonia, of which 17.4%, 13.2%, and 23.0% were double-eligible patients, respectively.
The rationale is that if community factors are responsible for readmission trends, then these need to be addressed. In contrast, according to the study, if the higher readmission rates were due to factors other than SDOH, the hospital may have controlled for those factors so that steps could be taken to improve these outcomes.
The census data the study relies on includes several SDOHs—race, ethnicity, and cultural background; socioeconomic status; social relationships; gender; and residential and community environment. However, there are other SDOHs that go beyond the scope of the study and the content of the census. For example, health literacy, social support, educational attainment, etc.
One company involved in the Yale work believes it has AI-driven technology that leverages broader SDOH beyond the census-level data used in this study. Suwanee, Georgia-based Jvion claims its data can provide clients with more comprehensive clinical decision-making capabilities.
“There are many underlying factors at play that cannot be accurately measured or explained by census data alone. Other factors, such as digital fluency and social distancing, are also hugely influential,” John Frownfelter, Jvion’s chief medical officer, said in an email. of social determinants that cannot be captured at the community level. “Awareness of things like social isolation enables providers to refer patients to support group services, which can help improve long-term health outcomes; while digital fluency can determine How much tele or telehealth services, if any, should be used (an important insight, especially after Covid). “
frown pointing out jevionThe technology looks at patients and their SDOH risk factors to identify overlooked differences that, when understood and addressed, have been shown to reduce readmission rates by as much as 20 percent, he said.
“Going forward, we need to combine these census-level findings with more granular, personalized data to accurately understand patients to identify and address various forms of inequity,” Frownfelter urged.
It’s not that the data isn’t available, he says, but that it needs to be compiled in a meaningful way. Jvion’s technology is designed to leverage AI to aggregate existing data about these additional SDOHs and compile and analyze it to help turn this information into actionable information.
“The directionality of AI is very important. The insights that AI provides at the community level are especially relevant to the substantial investments healthcare providers are making to improve communities and address health inequity challenges. Since zip code data is not sufficient to guide programmatic resources , so we need to drill down to the smaller community level or block group level, as we refer to here at Jvion,” Frownfelter said.
“For example, if we know that an entire zip code has no access to primary care providers and we’re opening a new clinic, the exact neighborhood with the worst access may be far from where the new clinic is located, even in the same zip code. Large geographic area Too heterogeneous to assume that any intervention on zip codes is ‘good enough’,” he added.
Frownfelter added that in addition to analyzing the data, AI also helps to integrate the data, which is especially useful in the current shortage of suppliers.
If disproportionate readmission rates among dual-eligible individuals can be attributed to other social determinants, hospitals may take actionable steps to promote equity. They could also explore ways to improve the quality of care transitions at discharge, according to research from Yale University.
Photo: South_agency, Getty Images
